Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    short phrases or sentences within quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    quoted phrases or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĻĤ
    -0.89
    Ļ½
    -0.88
    İĭ
    -0.70
    stant
    -0.68
    ¸
    -0.67
    ¿
    -0.66
    etheless
    -0.65
    ailing
    -0.65
    ¾
    -0.65
    mu
    -0.64
    POSITIVE LOGITS
    /"
    1.27
     moniker
    0.88
     aka
    0.78
     motto
    0.72
     ("
    0.72
     mantra
    0.72
    aneers
    0.67
    >>\
    0.65
     appell
    0.65
     refers
    0.64
    Act Density 0.093%

    No Known Activations